search

gooofy / zamia-speech

Open tools and data for cloudless automatic speech recognition
GNU Lesser General Public License v3.0
443 stars 86 forks source link

Batch Inference #109

Open rockiram opened 4 years ago

rockiram commented 4 years ago

Is it possible to run inference in batches instead of one by one?

If so please suggest me some approach.

gooofy commented 4 years ago

that is certainly possible and is in fact used to auto-review audio submissions. check out auto_review.py to get started.

rockiram commented 4 years ago

Thanks @gooofy for immediate reply. In auto_review.py, The audio files are processed one by one in for loop. Will it be possible to send multiple audio files in a single batch for prediction?